Merge branch 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6

Pull crypto updates from Herbert Xu:
 "API:
   - Allow DRBG testing through user-space af_alg
   - Add tcrypt speed testing support for keyed hashes
   - Add type-safe init/exit hooks for ahash

  Algorithms:
   - Mark arc4 as obsolete and pending for future removal
   - Mark anubis, khazad, sead and tea as obsolete
   - Improve boot-time xor benchmark
   - Add OSCCA SM2 asymmetric cipher algorithm and use it for integrity

  Drivers:
   - Fixes and enhancement for XTS in caam
   - Add support for XIP8001B hwrng in xiphera-trng
   - Add RNG and hash support in sun8i-ce/sun8i-ss
   - Allow imx-rngc to be used by kernel entropy pool
   - Use crypto engine in omap-sham
   - Add support for Ingenic X1830 with ingenic"

* 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (205 commits)
  X.509: Fix modular build of public_key_sm2
  crypto: xor - Remove unused variable count in do_xor_speed
  X.509: fix error return value on the failed path
  crypto: bcm - Verify GCM/CCM key length in setkey
  crypto: qat - drop input parameter from adf_enable_aer()
  crypto: qat - fix function parameters descriptions
  crypto: atmel-tdes - use semicolons rather than commas to separate statements
  crypto: drivers - use semicolons rather than commas to separate statements
  hwrng: mxc-rnga - use semicolons rather than commas to separate statements
  hwrng: iproc-rng200 - use semicolons rather than commas to separate statements
  hwrng: stm32 - use semicolons rather than commas to separate statements
  crypto: xor - use ktime for template benchmarking
  crypto: xor - defer load time benchmark to a later time
  crypto: hisilicon/zip - fix the uninitalized 'curr_qm_qp_num'
  crypto: hisilicon/zip - fix the return value when device is busy
  crypto: hisilicon/zip - fix zero length input in GZIP decompress
  crypto: hisilicon/zip - fix the uncleared debug registers
  lib/mpi: Fix unused variable warnings
  crypto: x86/poly1305 - Remove assignments with no effect
  hwrng: npcm - modify readl to readb
  ...

8 files changed, 50 insertions, 53 deletions

diff --git a/arch/x86/crypto/blake2s-glue.c b/arch/x86/crypto/blake2s-glue.c
index 6737bcea1fa1..c025a01cf708 100644
--- a/arch/x86/crypto/blake2s-glue.c
+++ b/arch/x86/crypto/blake2s-glue.c
@@ -11,6 +11,7 @@
 #include <linux/jump_label.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/sizes.h>
 
 #include <asm/cpufeature.h>
 #include <asm/fpu/api.h>
diff --git a/arch/x86/crypto/chacha_glue.c b/arch/x86/crypto/chacha_glue.c
index e67a59130025..7b3a1cf0984b 100644
--- a/arch/x86/crypto/chacha_glue.c
+++ b/arch/x86/crypto/chacha_glue.c
@@ -12,6 +12,7 @@
 #include <crypto/internal/skcipher.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/sizes.h>
 #include <asm/simd.h>
 
 asmlinkage void chacha_block_xor_ssse3(u32 *state, u8 *dst, const u8 *src,
diff --git a/arch/x86/crypto/crc32c-intel_glue.c b/arch/x86/crypto/crc32c-intel_glue.c
index d2d069bd459b..feccb5254c7e 100644
--- a/arch/x86/crypto/crc32c-intel_glue.c
+++ b/arch/x86/crypto/crc32c-intel_glue.c
@@ -28,9 +28,9 @@
 #define SCALE_F	sizeof(unsigned long)
 
 #ifdef CONFIG_X86_64
-#define REX_PRE "0x48, "
+#define CRC32_INST "crc32q %1, %q0"
 #else
-#define REX_PRE
+#define CRC32_INST "crc32l %1, %0"
 #endif
 
 #ifdef CONFIG_X86_64
@@ -48,11 +48,8 @@ asmlinkage unsigned int crc_pcl(const u8 *buffer, int len,
 static u32 crc32c_intel_le_hw_byte(u32 crc, unsigned char const *data, size_t length)
 {
 	while (length--) {
-		__asm__ __volatile__(
-			".byte 0xf2, 0xf, 0x38, 0xf0, 0xf1"
-			:"=S"(crc)
-			:"0"(crc), "c"(*data)
-		);
+		asm("crc32b %1, %0"
+		    : "+r" (crc) : "rm" (*data));
 		data++;
 	}
 
@@ -66,11 +63,8 @@ static u32 __pure crc32c_intel_le_hw(u32 crc, unsigned char const *p, size_t len
 	unsigned long *ptmp = (unsigned long *)p;
 
 	while (iquotient--) {
-		__asm__ __volatile__(
-			".byte 0xf2, " REX_PRE "0xf, 0x38, 0xf1, 0xf1;"
-			:"=S"(crc)
-			:"0"(crc), "c"(*ptmp)
-		);
+		asm(CRC32_INST
+		    : "+r" (crc) : "rm" (*ptmp));
 		ptmp++;
 	}
 
diff --git a/arch/x86/crypto/curve25519-x86_64.c b/arch/x86/crypto/curve25519-x86_64.c
index 8acbb6584a37..5af8021b98ce 100644
--- a/arch/x86/crypto/curve25519-x86_64.c
+++ b/arch/x86/crypto/curve25519-x86_64.c
@@ -11,6 +11,7 @@
 #include <linux/jump_label.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/scatterlist.h>
 
 #include <asm/cpufeature.h>
 #include <asm/processor.h>
@@ -45,11 +46,11 @@ static inline u64 add_scalar(u64 *out, const u64 *f1, u64 f2)
 
 	asm volatile(
 		/* Clear registers to propagate the carry bit */
-		"  xor %%r8, %%r8;"
-		"  xor %%r9, %%r9;"
-		"  xor %%r10, %%r10;"
-		"  xor %%r11, %%r11;"
-		"  xor %1, %1;"
+		"  xor %%r8d, %%r8d;"
+		"  xor %%r9d, %%r9d;"
+		"  xor %%r10d, %%r10d;"
+		"  xor %%r11d, %%r11d;"
+		"  xor %k1, %k1;"
 
 		/* Begin addition chain */
 		"  addq 0(%3), %0;"
@@ -93,7 +94,7 @@ static inline void fadd(u64 *out, const u64 *f1, const u64 *f2)
 		"  cmovc %0, %%rax;"
 
 		/* Step 2: Add carry*38 to the original sum */
-		"  xor %%rcx, %%rcx;"
+		"  xor %%ecx, %%ecx;"
 		"  add %%rax, %%r8;"
 		"  adcx %%rcx, %%r9;"
 		"  movq %%r9, 8(%1);"
@@ -165,28 +166,28 @@ static inline void fmul(u64 *out, const u64 *f1, const u64 *f2, u64 *tmp)
 
 		/* Compute src1[0] * src2 */
 		"  movq 0(%1), %%rdx;"
-		"  mulxq 0(%3), %%r8, %%r9;"       "  xor %%r10, %%r10;"     "  movq %%r8, 0(%0);"
+		"  mulxq 0(%3), %%r8, %%r9;"       "  xor %%r10d, %%r10d;"   "  movq %%r8, 0(%0);"
 		"  mulxq 8(%3), %%r10, %%r11;"     "  adox %%r9, %%r10;"     "  movq %%r10, 8(%0);"
 		"  mulxq 16(%3), %%rbx, %%r13;"    "  adox %%r11, %%rbx;"
 		"  mulxq 24(%3), %%r14, %%rdx;"    "  adox %%r13, %%r14;"    "  mov $0, %%rax;"
 		                                   "  adox %%rdx, %%rax;"
 		/* Compute src1[1] * src2 */
 		"  movq 8(%1), %%rdx;"
-		"  mulxq 0(%3), %%r8, %%r9;"       "  xor %%r10, %%r10;"     "  adcxq 8(%0), %%r8;"    "  movq %%r8, 8(%0);"
+		"  mulxq 0(%3), %%r8, %%r9;"       "  xor %%r10d, %%r10d;"   "  adcxq 8(%0), %%r8;"    "  movq %%r8, 8(%0);"
 		"  mulxq 8(%3), %%r10, %%r11;"     "  adox %%r9, %%r10;"     "  adcx %%rbx, %%r10;"    "  movq %%r10, 16(%0);"
 		"  mulxq 16(%3), %%rbx, %%r13;"    "  adox %%r11, %%rbx;"    "  adcx %%r14, %%rbx;"    "  mov $0, %%r8;"
 		"  mulxq 24(%3), %%r14, %%rdx;"    "  adox %%r13, %%r14;"    "  adcx %%rax, %%r14;"    "  mov $0, %%rax;"
 		                                   "  adox %%rdx, %%rax;"    "  adcx %%r8, %%rax;"
 		/* Compute src1[2] * src2 */
 		"  movq 16(%1), %%rdx;"
-		"  mulxq 0(%3), %%r8, %%r9;"       "  xor %%r10, %%r10;"    "  adcxq 16(%0), %%r8;"    "  movq %%r8, 16(%0);"
+		"  mulxq 0(%3), %%r8, %%r9;"       "  xor %%r10d, %%r10d;"   "  adcxq 16(%0), %%r8;"   "  movq %%r8, 16(%0);"
 		"  mulxq 8(%3), %%r10, %%r11;"     "  adox %%r9, %%r10;"     "  adcx %%rbx, %%r10;"    "  movq %%r10, 24(%0);"
 		"  mulxq 16(%3), %%rbx, %%r13;"    "  adox %%r11, %%rbx;"    "  adcx %%r14, %%rbx;"    "  mov $0, %%r8;"
 		"  mulxq 24(%3), %%r14, %%rdx;"    "  adox %%r13, %%r14;"    "  adcx %%rax, %%r14;"    "  mov $0, %%rax;"
 		                                   "  adox %%rdx, %%rax;"    "  adcx %%r8, %%rax;"
 		/* Compute src1[3] * src2 */
 		"  movq 24(%1), %%rdx;"
-		"  mulxq 0(%3), %%r8, %%r9;"       "  xor %%r10, %%r10;"    "  adcxq 24(%0), %%r8;"    "  movq %%r8, 24(%0);"
+		"  mulxq 0(%3), %%r8, %%r9;"       "  xor %%r10d, %%r10d;"   "  adcxq 24(%0), %%r8;"   "  movq %%r8, 24(%0);"
 		"  mulxq 8(%3), %%r10, %%r11;"     "  adox %%r9, %%r10;"     "  adcx %%rbx, %%r10;"    "  movq %%r10, 32(%0);"
 		"  mulxq 16(%3), %%rbx, %%r13;"    "  adox %%r11, %%rbx;"    "  adcx %%r14, %%rbx;"    "  movq %%rbx, 40(%0);"    "  mov $0, %%r8;"
 		"  mulxq 24(%3), %%r14, %%rdx;"    "  adox %%r13, %%r14;"    "  adcx %%rax, %%r14;"    "  movq %%r14, 48(%0);"    "  mov $0, %%rax;"
@@ -200,7 +201,7 @@ static inline void fmul(u64 *out, const u64 *f1, const u64 *f2, u64 *tmp)
 		/* Step 1: Compute dst + carry == tmp_hi * 38 + tmp_lo */
 		"  mov $38, %%rdx;"
 		"  mulxq 32(%1), %%r8, %%r13;"
-		"  xor %3, %3;"
+		"  xor %k3, %k3;"
 		"  adoxq 0(%1), %%r8;"
 		"  mulxq 40(%1), %%r9, %%rbx;"
 		"  adcx %%r13, %%r9;"
@@ -246,28 +247,28 @@ static inline void fmul2(u64 *out, const u64 *f1, const u64 *f2, u64 *tmp)
 
 		/* Compute src1[0] * src2 */
 		"  movq 0(%1), %%rdx;"
-		"  mulxq 0(%3), %%r8, %%r9;"       "  xor %%r10, %%r10;"     "  movq %%r8, 0(%0);"
+		"  mulxq 0(%3), %%r8, %%r9;"       "  xor %%r10d, %%r10d;"   "  movq %%r8, 0(%0);"
 		"  mulxq 8(%3), %%r10, %%r11;"     "  adox %%r9, %%r10;"     "  movq %%r10, 8(%0);"
 		"  mulxq 16(%3), %%rbx, %%r13;"    "  adox %%r11, %%rbx;"
 		"  mulxq 24(%3), %%r14, %%rdx;"    "  adox %%r13, %%r14;"    "  mov $0, %%rax;"
 		                                   "  adox %%rdx, %%rax;"
 		/* Compute src1[1] * src2 */
 		"  movq 8(%1), %%rdx;"
-		"  mulxq 0(%3), %%r8, %%r9;"       "  xor %%r10, %%r10;"     "  adcxq 8(%0), %%r8;"    "  movq %%r8, 8(%0);"
+		"  mulxq 0(%3), %%r8, %%r9;"       "  xor %%r10d, %%r10d;"   "  adcxq 8(%0), %%r8;"    "  movq %%r8, 8(%0);"
 		"  mulxq 8(%3), %%r10, %%r11;"     "  adox %%r9, %%r10;"     "  adcx %%rbx, %%r10;"    "  movq %%r10, 16(%0);"
 		"  mulxq 16(%3), %%rbx, %%r13;"    "  adox %%r11, %%rbx;"    "  adcx %%r14, %%rbx;"    "  mov $0, %%r8;"
 		"  mulxq 24(%3), %%r14, %%rdx;"    "  adox %%r13, %%r14;"    "  adcx %%rax, %%r14;"    "  mov $0, %%rax;"
 		                                   "  adox %%rdx, %%rax;"    "  adcx %%r8, %%rax;"
 		/* Compute src1[2] * src2 */
 		"  movq 16(%1), %%rdx;"
-		"  mulxq 0(%3), %%r8, %%r9;"       "  xor %%r10, %%r10;"    "  adcxq 16(%0), %%r8;"    "  movq %%r8, 16(%0);"
+		"  mulxq 0(%3), %%r8, %%r9;"       "  xor %%r10d, %%r10d;"   "  adcxq 16(%0), %%r8;"   "  movq %%r8, 16(%0);"
 		"  mulxq 8(%3), %%r10, %%r11;"     "  adox %%r9, %%r10;"     "  adcx %%rbx, %%r10;"    "  movq %%r10, 24(%0);"
 		"  mulxq 16(%3), %%rbx, %%r13;"    "  adox %%r11, %%rbx;"    "  adcx %%r14, %%rbx;"    "  mov $0, %%r8;"
 		"  mulxq 24(%3), %%r14, %%rdx;"    "  adox %%r13, %%r14;"    "  adcx %%rax, %%r14;"    "  mov $0, %%rax;"
 		                                   "  adox %%rdx, %%rax;"    "  adcx %%r8, %%rax;"
 		/* Compute src1[3] * src2 */
 		"  movq 24(%1), %%rdx;"
-		"  mulxq 0(%3), %%r8, %%r9;"       "  xor %%r10, %%r10;"    "  adcxq 24(%0), %%r8;"    "  movq %%r8, 24(%0);"
+		"  mulxq 0(%3), %%r8, %%r9;"       "  xor %%r10d, %%r10d;"   "  adcxq 24(%0), %%r8;"   "  movq %%r8, 24(%0);"
 		"  mulxq 8(%3), %%r10, %%r11;"     "  adox %%r9, %%r10;"     "  adcx %%rbx, %%r10;"    "  movq %%r10, 32(%0);"
 		"  mulxq 16(%3), %%rbx, %%r13;"    "  adox %%r11, %%rbx;"    "  adcx %%r14, %%rbx;"    "  movq %%rbx, 40(%0);"    "  mov $0, %%r8;"
 		"  mulxq 24(%3), %%r14, %%rdx;"    "  adox %%r13, %%r14;"    "  adcx %%rax, %%r14;"    "  movq %%r14, 48(%0);"    "  mov $0, %%rax;"
@@ -277,29 +278,29 @@ static inline void fmul2(u64 *out, const u64 *f1, const u64 *f2, u64 *tmp)
 
 		/* Compute src1[0] * src2 */
 		"  movq 32(%1), %%rdx;"
-		"  mulxq 32(%3), %%r8, %%r9;"       "  xor %%r10, %%r10;"     "  movq %%r8, 64(%0);"
-		"  mulxq 40(%3), %%r10, %%r11;"     "  adox %%r9, %%r10;"     "  movq %%r10, 72(%0);"
+		"  mulxq 32(%3), %%r8, %%r9;"      "  xor %%r10d, %%r10d;"   "  movq %%r8, 64(%0);"
+		"  mulxq 40(%3), %%r10, %%r11;"    "  adox %%r9, %%r10;"     "  movq %%r10, 72(%0);"
 		"  mulxq 48(%3), %%rbx, %%r13;"    "  adox %%r11, %%rbx;"
 		"  mulxq 56(%3), %%r14, %%rdx;"    "  adox %%r13, %%r14;"    "  mov $0, %%rax;"
 		                                   "  adox %%rdx, %%rax;"
 		/* Compute src1[1] * src2 */
 		"  movq 40(%1), %%rdx;"
-		"  mulxq 32(%3), %%r8, %%r9;"       "  xor %%r10, %%r10;"     "  adcxq 72(%0), %%r8;"    "  movq %%r8, 72(%0);"
-		"  mulxq 40(%3), %%r10, %%r11;"     "  adox %%r9, %%r10;"     "  adcx %%rbx, %%r10;"    "  movq %%r10, 80(%0);"
+		"  mulxq 32(%3), %%r8, %%r9;"      "  xor %%r10d, %%r10d;"   "  adcxq 72(%0), %%r8;"   "  movq %%r8, 72(%0);"
+		"  mulxq 40(%3), %%r10, %%r11;"    "  adox %%r9, %%r10;"     "  adcx %%rbx, %%r10;"    "  movq %%r10, 80(%0);"
 		"  mulxq 48(%3), %%rbx, %%r13;"    "  adox %%r11, %%rbx;"    "  adcx %%r14, %%rbx;"    "  mov $0, %%r8;"
 		"  mulxq 56(%3), %%r14, %%rdx;"    "  adox %%r13, %%r14;"    "  adcx %%rax, %%r14;"    "  mov $0, %%rax;"
 		                                   "  adox %%rdx, %%rax;"    "  adcx %%r8, %%rax;"
 		/* Compute src1[2] * src2 */
 		"  movq 48(%1), %%rdx;"
-		"  mulxq 32(%3), %%r8, %%r9;"       "  xor %%r10, %%r10;"    "  adcxq 80(%0), %%r8;"    "  movq %%r8, 80(%0);"
-		"  mulxq 40(%3), %%r10, %%r11;"     "  adox %%r9, %%r10;"     "  adcx %%rbx, %%r10;"    "  movq %%r10, 88(%0);"
+		"  mulxq 32(%3), %%r8, %%r9;"      "  xor %%r10d, %%r10d;"   "  adcxq 80(%0), %%r8;"   "  movq %%r8, 80(%0);"
+		"  mulxq 40(%3), %%r10, %%r11;"    "  adox %%r9, %%r10;"     "  adcx %%rbx, %%r10;"    "  movq %%r10, 88(%0);"
 		"  mulxq 48(%3), %%rbx, %%r13;"    "  adox %%r11, %%rbx;"    "  adcx %%r14, %%rbx;"    "  mov $0, %%r8;"
 		"  mulxq 56(%3), %%r14, %%rdx;"    "  adox %%r13, %%r14;"    "  adcx %%rax, %%r14;"    "  mov $0, %%rax;"
 		                                   "  adox %%rdx, %%rax;"    "  adcx %%r8, %%rax;"
 		/* Compute src1[3] * src2 */
 		"  movq 56(%1), %%rdx;"
-		"  mulxq 32(%3), %%r8, %%r9;"       "  xor %%r10, %%r10;"    "  adcxq 88(%0), %%r8;"    "  movq %%r8, 88(%0);"
-		"  mulxq 40(%3), %%r10, %%r11;"     "  adox %%r9, %%r10;"     "  adcx %%rbx, %%r10;"    "  movq %%r10, 96(%0);"
+		"  mulxq 32(%3), %%r8, %%r9;"      "  xor %%r10d, %%r10d;"   "  adcxq 88(%0), %%r8;"   "  movq %%r8, 88(%0);"
+		"  mulxq 40(%3), %%r10, %%r11;"    "  adox %%r9, %%r10;"     "  adcx %%rbx, %%r10;"    "  movq %%r10, 96(%0);"
 		"  mulxq 48(%3), %%rbx, %%r13;"    "  adox %%r11, %%rbx;"    "  adcx %%r14, %%rbx;"    "  movq %%rbx, 104(%0);"    "  mov $0, %%r8;"
 		"  mulxq 56(%3), %%r14, %%rdx;"    "  adox %%r13, %%r14;"    "  adcx %%rax, %%r14;"    "  movq %%r14, 112(%0);"    "  mov $0, %%rax;"
 		                                   "  adox %%rdx, %%rax;"    "  adcx %%r8, %%rax;"     "  movq %%rax, 120(%0);"
@@ -312,7 +313,7 @@ static inline void fmul2(u64 *out, const u64 *f1, const u64 *f2, u64 *tmp)
 		/* Step 1: Compute dst + carry == tmp_hi * 38 + tmp_lo */
 		"  mov $38, %%rdx;"
 		"  mulxq 32(%1), %%r8, %%r13;"
-		"  xor %3, %3;"
+		"  xor %k3, %k3;"
 		"  adoxq 0(%1), %%r8;"
 		"  mulxq 40(%1), %%r9, %%rbx;"
 		"  adcx %%r13, %%r9;"
@@ -345,7 +346,7 @@ static inline void fmul2(u64 *out, const u64 *f1, const u64 *f2, u64 *tmp)
 		/* Step 1: Compute dst + carry == tmp_hi * 38 + tmp_lo */
 		"  mov $38, %%rdx;"
 		"  mulxq 96(%1), %%r8, %%r13;"
-		"  xor %3, %3;"
+		"  xor %k3, %k3;"
 		"  adoxq 64(%1), %%r8;"
 		"  mulxq 104(%1), %%r9, %%rbx;"
 		"  adcx %%r13, %%r9;"
@@ -516,7 +517,7 @@ static inline void fsqr(u64 *out, const u64 *f, u64 *tmp)
 
 		/* Step 1: Compute all partial products */
 		"  movq 0(%1), %%rdx;"                                       /* f[0] */
-		"  mulxq 8(%1), %%r8, %%r14;"      "  xor %%r15, %%r15;"     /* f[1]*f[0] */
+		"  mulxq 8(%1), %%r8, %%r14;"      "  xor %%r15d, %%r15d;"   /* f[1]*f[0] */
 		"  mulxq 16(%1), %%r9, %%r10;"     "  adcx %%r14, %%r9;"     /* f[2]*f[0] */
 		"  mulxq 24(%1), %%rax, %%rcx;"    "  adcx %%rax, %%r10;"    /* f[3]*f[0] */
 		"  movq 24(%1), %%rdx;"                                      /* f[3] */
@@ -526,7 +527,7 @@ static inline void fsqr(u64 *out, const u64 *f, u64 *tmp)
 		"  mulxq 16(%1), %%rax, %%rcx;"    "  mov $0, %%r14;"        /* f[2]*f[1] */
 
 		/* Step 2: Compute two parallel carry chains */
-		"  xor %%r15, %%r15;"
+		"  xor %%r15d, %%r15d;"
 		"  adox %%rax, %%r10;"
 		"  adcx %%r8, %%r8;"
 		"  adox %%rcx, %%r11;"
@@ -563,7 +564,7 @@ static inline void fsqr(u64 *out, const u64 *f, u64 *tmp)
 		/* Step 1: Compute dst + carry == tmp_hi * 38 + tmp_lo */
 		"  mov $38, %%rdx;"
 		"  mulxq 32(%1), %%r8, %%r13;"
-		"  xor %%rcx, %%rcx;"
+		"  xor %%ecx, %%ecx;"
 		"  adoxq 0(%1), %%r8;"
 		"  mulxq 40(%1), %%r9, %%rbx;"
 		"  adcx %%r13, %%r9;"
@@ -607,7 +608,7 @@ static inline void fsqr2(u64 *out, const u64 *f, u64 *tmp)
 	asm volatile(
 		/* Step 1: Compute all partial products */
 		"  movq 0(%1), %%rdx;"                                       /* f[0] */
-		"  mulxq 8(%1), %%r8, %%r14;"      "  xor %%r15, %%r15;"     /* f[1]*f[0] */
+		"  mulxq 8(%1), %%r8, %%r14;"      "  xor %%r15d, %%r15d;"   /* f[1]*f[0] */
 		"  mulxq 16(%1), %%r9, %%r10;"     "  adcx %%r14, %%r9;"     /* f[2]*f[0] */
 		"  mulxq 24(%1), %%rax, %%rcx;"    "  adcx %%rax, %%r10;"    /* f[3]*f[0] */
 		"  movq 24(%1), %%rdx;"                                      /* f[3] */
@@ -617,7 +618,7 @@ static inline void fsqr2(u64 *out, const u64 *f, u64 *tmp)
 		"  mulxq 16(%1), %%rax, %%rcx;"    "  mov $0, %%r14;"        /* f[2]*f[1] */
 
 		/* Step 2: Compute two parallel carry chains */
-		"  xor %%r15, %%r15;"
+		"  xor %%r15d, %%r15d;"
 		"  adox %%rax, %%r10;"
 		"  adcx %%r8, %%r8;"
 		"  adox %%rcx, %%r11;"
@@ -647,7 +648,7 @@ static inline void fsqr2(u64 *out, const u64 *f, u64 *tmp)
 
 		/* Step 1: Compute all partial products */
 		"  movq 32(%1), %%rdx;"                                       /* f[0] */
-		"  mulxq 40(%1), %%r8, %%r14;"      "  xor %%r15, %%r15;"     /* f[1]*f[0] */
+		"  mulxq 40(%1), %%r8, %%r14;"     "  xor %%r15d, %%r15d;"   /* f[1]*f[0] */
 		"  mulxq 48(%1), %%r9, %%r10;"     "  adcx %%r14, %%r9;"     /* f[2]*f[0] */
 		"  mulxq 56(%1), %%rax, %%rcx;"    "  adcx %%rax, %%r10;"    /* f[3]*f[0] */
 		"  movq 56(%1), %%rdx;"                                      /* f[3] */
@@ -657,7 +658,7 @@ static inline void fsqr2(u64 *out, const u64 *f, u64 *tmp)
 		"  mulxq 48(%1), %%rax, %%rcx;"    "  mov $0, %%r14;"        /* f[2]*f[1] */
 
 		/* Step 2: Compute two parallel carry chains */
-		"  xor %%r15, %%r15;"
+		"  xor %%r15d, %%r15d;"
 		"  adox %%rax, %%r10;"
 		"  adcx %%r8, %%r8;"
 		"  adox %%rcx, %%r11;"
@@ -692,7 +693,7 @@ static inline void fsqr2(u64 *out, const u64 *f, u64 *tmp)
 		/* Step 1: Compute dst + carry == tmp_hi * 38 + tmp_lo */
 		"  mov $38, %%rdx;"
 		"  mulxq 32(%1), %%r8, %%r13;"
-		"  xor %%rcx, %%rcx;"
+		"  xor %%ecx, %%ecx;"
 		"  adoxq 0(%1), %%r8;"
 		"  mulxq 40(%1), %%r9, %%rbx;"
 		"  adcx %%r13, %%r9;"
@@ -725,7 +726,7 @@ static inline void fsqr2(u64 *out, const u64 *f, u64 *tmp)
 		/* Step 1: Compute dst + carry == tmp_hi * 38 + tmp_lo */
 		"  mov $38, %%rdx;"
 		"  mulxq 96(%1), %%r8, %%r13;"
-		"  xor %%rcx, %%rcx;"
+		"  xor %%ecx, %%ecx;"
 		"  adoxq 64(%1), %%r8;"
 		"  mulxq 104(%1), %%r9, %%rbx;"
 		"  adcx %%r13, %%r9;"
diff --git a/arch/x86/crypto/nhpoly1305-avx2-glue.c b/arch/x86/crypto/nhpoly1305-avx2-glue.c
index 80fcb85736e1..8ea5ab0f1ca7 100644
--- a/arch/x86/crypto/nhpoly1305-avx2-glue.c
+++ b/arch/x86/crypto/nhpoly1305-avx2-glue.c
@@ -10,6 +10,7 @@
 #include <crypto/internal/simd.h>
 #include <crypto/nhpoly1305.h>
 #include <linux/module.h>
+#include <linux/sizes.h>
 #include <asm/simd.h>
 
 asmlinkage void nh_avx2(const u32 *key, const u8 *message, size_t message_len,
diff --git a/arch/x86/crypto/nhpoly1305-sse2-glue.c b/arch/x86/crypto/nhpoly1305-sse2-glue.c
index cc6b7c1a2705..2b353d42ed13 100644
--- a/arch/x86/crypto/nhpoly1305-sse2-glue.c
+++ b/arch/x86/crypto/nhpoly1305-sse2-glue.c
@@ -10,6 +10,7 @@
 #include <crypto/internal/simd.h>
 #include <crypto/nhpoly1305.h>
 #include <linux/module.h>
+#include <linux/sizes.h>
 #include <asm/simd.h>
 
 asmlinkage void nh_sse2(const u32 *key, const u8 *message, size_t message_len,
diff --git a/arch/x86/crypto/poly1305-x86_64-cryptogams.pl b/arch/x86/crypto/poly1305-x86_64-cryptogams.pl
index 137edcf038cb..7d568012cc15 100644
--- a/arch/x86/crypto/poly1305-x86_64-cryptogams.pl
+++ b/arch/x86/crypto/poly1305-x86_64-cryptogams.pl
@@ -246,7 +246,7 @@ $code.=<<___ if (!$kernel);
 ___
 &declare_function("poly1305_init_x86_64", 32, 3);
 $code.=<<___;
-	xor	%rax,%rax
+	xor	%eax,%eax
 	mov	%rax,0($ctx)		# initialize hash value
 	mov	%rax,8($ctx)
 	mov	%rax,16($ctx)
@@ -2853,7 +2853,7 @@ $code.=<<___;
 .type	poly1305_init_base2_44,\@function,3
 .align	32
 poly1305_init_base2_44:
-	xor	%rax,%rax
+	xor	%eax,%eax
 	mov	%rax,0($ctx)		# initialize hash value
 	mov	%rax,8($ctx)
 	mov	%rax,16($ctx)
@@ -3947,7 +3947,7 @@ xor128_decrypt_n_pad:
 	mov	\$16,$len
 	sub	%r10,$len
 	xor	%eax,%eax
-	xor	%r11,%r11
+	xor	%r11d,%r11d
 .Loop_dec_byte:
 	mov	($inp,$otp),%r11b
 	mov	($otp),%al
@@ -4085,7 +4085,7 @@ avx_handler:
 	.long	0xa548f3fc		# cld; rep movsq
 
 	mov	$disp,%rsi
-	xor	%rcx,%rcx		# arg1, UNW_FLAG_NHANDLER
+	xor	%ecx,%ecx		# arg1, UNW_FLAG_NHANDLER
 	mov	8(%rsi),%rdx		# arg2, disp->ImageBase
 	mov	0(%rsi),%r8		# arg3, disp->ControlPc
 	mov	16(%rsi),%r9		# arg4, disp->FunctionEntry
diff --git a/arch/x86/crypto/poly1305_glue.c b/arch/x86/crypto/poly1305_glue.c
index dfe921efa9b2..e508dbd91813 100644
--- a/arch/x86/crypto/poly1305_glue.c
+++ b/arch/x86/crypto/poly1305_glue.c
@@ -11,6 +11,7 @@
 #include <linux/jump_label.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/sizes.h>
 #include <asm/intel-family.h>
 #include <asm/simd.h>
 
@@ -157,9 +158,6 @@ static unsigned int crypto_poly1305_setdctxkey(struct poly1305_desc_ctx *dctx,
 			dctx->s[1] = get_unaligned_le32(&inp[4]);
 			dctx->s[2] = get_unaligned_le32(&inp[8]);
 			dctx->s[3] = get_unaligned_le32(&inp[12]);
-			inp += POLY1305_BLOCK_SIZE;
-			len -= POLY1305_BLOCK_SIZE;
-			acc += POLY1305_BLOCK_SIZE;
 			dctx->sset = true;
 		}
 	}